Related papers: Reward-Free Attacks in Multi-Agent Reinforcement L…
Reinforcement learning (RL) has achieved remarkable success in fields like robotics and autonomous driving, but adversarial attacks designed to mislead RL systems remain challenging. Existing approaches often rely on modifying the…
This paper investigates the use of intrinsic reward to guide exploration in multi-agent reinforcement learning. We discuss the challenges in applying intrinsic reward to multiple collaborative agents and demonstrate how unreliable reward…
We consider a multi-player multi-armed bandit setting in the presence of adversaries that attempt to negatively affect the rewards received by the players in the system. The reward distributions for any given arm are heterogeneous across…
We consider the classical multi-armed bandit problem, but with strategic arms. In this context, each arm is characterized by a bounded support reward distribution and strategically aims to maximize its own utility by potentially retaining a…
Despite the increasing popularity of policy gradient methods, they are yet to be widely utilized in sample-scarce applications, such as robotics. The sample efficiency could be improved by making best usage of available information. As a…
We study the challenging exploration incentive problem in both bandit and reinforcement learning, where the rewards are scale-free and potentially unbounded, driven by real-world scenarios and differing from existing work. Past works in…
Robots must know how to be gentle when they need to interact with fragile objects, or when the robot itself is prone to wear and tear. We propose an approach that enables deep reinforcement learning to train policies that are gentle, both…
In reinforcement learning, we typically aim to optimize the expected value of the sum of rewards an agent collects over a trajectory. However, if the process generating these rewards is non-ergodic, the expected value, i.e., the average…
We consider the problem of learning to behave optimally in a Markov Decision Process when a reward function is not specified, but instead we have access to a set of demonstrators of varying performance. We assume the demonstrators are…
Reward models (RMs) are widely used as optimization targets in reinforcement learning from human feedback (RLHF), yet they remain vulnerable to reward hacking. Existing attacks mainly operate within the semantic space, constructing…
Motivated by applications in cyber security, we develop a simple game model for describing how a learning agent's private information influences an observing agent's inference process. The model describes a situation in which one of the…
In targeted poisoning attacks, an attacker manipulates an agent-environment interaction to force the agent into adopting a policy of interest, called target policy. Prior work has primarily focused on attacks that modify standard MDP…
Finding optimal adversarial attack strategies is an important topic in reinforcement learning and the Markov decision process. Previous studies usually assume one all-knowing coordinator (attacker) for whom attacking different recipient…
In this paper we study how transforming regular reinforcement learning environments into goal-conditioned environments can let agents learn to solve tasks autonomously and reward-free. We show that an agent can learn to solve tasks by…
Existing imitation learning approaches often require that the complete demonstration data, including sequences of actions and states, are available. In this paper, we consider a more realistic and difficult scenario where a reinforcement…
Reinforcement learning (RL) relies heavily on exploration to learn from its environment and maximize observed rewards. Therefore, it is essential to design a reward function that guarantees optimal learning from the received experience.…
In reinforcement learning (RL), an agent learns to perform a task by interacting with an environment and receiving feedback (a numerical reward) for its actions. However, the assumption that rewards are always observable is often not…
We study reward poisoning attacks in reinforcement learning (RL), where an adversary manipulates rewards within constrained budgets to force the target RL agent to adopt a policy that aligns with the attacker's objectives. Prior works on…
Agentic reinforcement learning (RL) for Large Language Models (LLMs) critically depends on the exploration capability of the base policy, as training signals emerge only within its in-capability region. For tasks where the base policy…
Recent trends in Reinforcement Learning (RL) highlight the need for agents to learn from reward-free interactions and alternative supervision signals, such as unlabeled or incomplete demonstrations, rather than relying solely on explicit…